Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6747
    Prev
    Next
    INDEX
    Explanations

    terms related to research and scientific inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.90
    ########.
    -0.78
    ก่
    -0.70
     Countess
    -0.68
     bint
    -0.67
    ElementException
    -0.66
     GeoNames
    -0.65
     Estuary
    -0.65
     Jovi
    -0.64
     Diocese
    -0.64
    POSITIVE LOGITS
     research
    3.50
     Research
    3.16
    research
    3.05
    Research
    3.04
     RESEARCH
    2.82
    RESEARCH
    2.72
     researches
    2.36
     researched
    2.21
     Forschung
    2.13
     researchers
    2.13
    Activations Density 0.081%

    No Known Activations